import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px 

import warnings
warnings.filterwarnings("ignore")

Read the dataset

data = pd.read_csv("../Spotify Music Dataset/data/data.csv")
genre_data = pd.read_csv('../Spotify Music Dataset/data_by_genres.csv')
year_data = pd.read_csv('../Spotify Music Dataset/data_by_year.csv')
artist_data = pd.read_csv('../Spotify Music Dataset/data_by_artist/data_by_artist.csv')

data.head(5)

	valence	year	acousticness	artists	danceability	duration_ms	energy	explicit	id	instrumentalness	key	liveness	loudness	mode	name	popularity	release_date	speechiness	tempo
0	0.0594	1921	0.982	['Sergei Rachmaninoff', 'James Levine', 'Berli...	0.279	831667	0.211	0	4BJqT0PrAfrxzMOxytFOIz	0.878000	10	0.665	-20.096	1	Piano Concerto No. 3 in D Minor, Op. 30: III. ...	4	1921	0.0366	80.954
1	0.9630	1921	0.732	['Dennis Day']	0.819	180533	0.341	0	7xPhfUan2yNtyFG0cUWkt8	0.000000	7	0.160	-12.441	1	Clancy Lowered the Boom	5	1921	0.4150	60.936
2	0.0394	1921	0.961	['KHP Kridhamardawa Karaton Ngayogyakarta Hadi...	0.328	500062	0.166	0	1o6I8BglA6ylDMrIELygv1	0.913000	3	0.101	-14.850	1	Gati Bali	5	1921	0.0339	110.339
3	0.1650	1921	0.967	['Frank Parker']	0.275	210000	0.309	0	3ftBPsC5vPBKxYSee08FDH	0.000028	5	0.381	-9.316	1	Danny Boy	3	1921	0.0354	100.109
4	0.2530	1921	0.957	['Phil Regan']	0.418	166693	0.193	0	4d6HGyGT8e121BsdKmw9v6	0.000002	3	0.229	-10.096	1	When Irish Eyes Are Smiling	2	1921	0.0380	101.665

The below table shows the description and distribution of data overall.

data.describe()

	valence	year	acousticness	danceability	duration_ms	energy	explicit	instrumentalness	key	liveness	loudness	mode	popularity	speechiness	tempo
count	170653.000000	170653.000000	170653.000000	170653.000000	1.706530e+05	170653.000000	170653.000000	170653.000000	170653.000000	170653.000000	170653.000000	170653.000000	170653.000000	170653.000000	170653.000000
mean	0.528587	1976.787241	0.502115	0.537396	2.309483e+05	0.482389	0.084575	0.167010	5.199844	0.205839	-11.467990	0.706902	31.431794	0.098393	116.861590
std	0.263171	25.917853	0.376032	0.176138	1.261184e+05	0.267646	0.278249	0.313475	3.515094	0.174805	5.697943	0.455184	21.826615	0.162740	30.708533
min	0.000000	1921.000000	0.000000	0.000000	5.108000e+03	0.000000	0.000000	0.000000	0.000000	0.000000	-60.000000	0.000000	0.000000	0.000000	0.000000
25%	0.317000	1956.000000	0.102000	0.415000	1.698270e+05	0.255000	0.000000	0.000000	2.000000	0.098800	-14.615000	0.000000	11.000000	0.034900	93.421000
50%	0.540000	1977.000000	0.516000	0.548000	2.074670e+05	0.471000	0.000000	0.000216	5.000000	0.136000	-10.580000	1.000000	33.000000	0.045000	114.729000
75%	0.747000	1999.000000	0.893000	0.668000	2.624000e+05	0.703000	0.000000	0.102000	8.000000	0.261000	-7.183000	1.000000	48.000000	0.075600	135.537000
max	1.000000	2020.000000	0.996000	0.988000	5.403500e+06	1.000000	1.000000	1.000000	11.000000	1.000000	3.855000	1.000000	100.000000	0.970000	243.507000

data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 170653 entries, 0 to 170652
Data columns (total 19 columns):
 #   Column            Non-Null Count   Dtype  
---  ------            --------------   -----  
 0   valence           170653 non-null  float64
 1   year              170653 non-null  int64  
 2   acousticness      170653 non-null  float64
 3   artists           170653 non-null  object 
 4   danceability      170653 non-null  float64
 5   duration_ms       170653 non-null  int64  
 6   energy            170653 non-null  float64
 7   explicit          170653 non-null  int64  
 8   id                170653 non-null  object 
 9   instrumentalness  170653 non-null  float64
 10  key               170653 non-null  int64  
 11  liveness          170653 non-null  float64
 12  loudness          170653 non-null  float64
 13  mode              170653 non-null  int64  
 14  name              170653 non-null  object 
 15  popularity        170653 non-null  int64  
 16  release_date      170653 non-null  object 
 17  speechiness       170653 non-null  float64
 18  tempo             170653 non-null  float64
dtypes: float64(9), int64(6), object(4)
memory usage: 24.7+ MB

genre_data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 2973 entries, 0 to 2972
Data columns (total 14 columns):
 #   Column            Non-Null Count  Dtype  
---  ------            --------------  -----  
 0   mode              2973 non-null   int64  
 1   genres            2973 non-null   object 
 2   acousticness      2973 non-null   float64
 3   danceability      2973 non-null   float64
 4   duration_ms       2973 non-null   float64
 5   energy            2973 non-null   float64
 6   instrumentalness  2973 non-null   float64
 7   liveness          2973 non-null   float64
 8   loudness          2973 non-null   float64
 9   speechiness       2973 non-null   float64
 10  tempo             2973 non-null   float64
 11  valence           2973 non-null   float64
 12  popularity        2973 non-null   float64
 13  key               2973 non-null   int64  
dtypes: float64(11), int64(2), object(1)
memory usage: 325.3+ KB

year_data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 100 entries, 0 to 99
Data columns (total 14 columns):
 #   Column            Non-Null Count  Dtype  
---  ------            --------------  -----  
 0   mode              100 non-null    int64  
 1   year              100 non-null    int64  
 2   acousticness      100 non-null    float64
 3   danceability      100 non-null    float64
 4   duration_ms       100 non-null    float64
 5   energy            100 non-null    float64
 6   instrumentalness  100 non-null    float64
 7   liveness          100 non-null    float64
 8   loudness          100 non-null    float64
 9   speechiness       100 non-null    float64
 10  tempo             100 non-null    float64
 11  valence           100 non-null    float64
 12  popularity        100 non-null    float64
 13  key               100 non-null    int64  
dtypes: float64(11), int64(3)
memory usage: 11.1 KB

Box plot of various music features to see the outliers and range of values

plt.figure(figsize=(14,6))
boxplot = data.boxplot(column=['valence','acousticness','danceability','energy','explicit','instrumentalness','liveness','speechiness'])
plt.show()

Correlation between the various music features of dataframe

# Compute the correlation matrix
corr = data.corr()

# Generate a mask for the upper triangle
mask = np.triu(np.ones_like(corr, dtype=bool))

f, ax = plt.subplots(figsize=(7, 9)) # Set up the matplotlib figure
cmap = sns.diverging_palette(230, 20, as_cmap=True) # Generate a custom diverging colormap

# Draw the heatmap with the mask and correct aspect ratio
sns.heatmap(corr, mask=mask, cmap=cmap, vmax=.3, center=0,
            square=True, linewidths=.5, cbar_kws={"shrink": .5})
plt.show()

We'll keep the target as 'popularity' for the future analysis.

Now, let's do the Feature Correlation by considering a few features using the yellowbrick package

!pip install yellowbrick

Requirement already satisfied: yellowbrick in c:\users\prakh\anaconda3\lib\site-packages (1.5)
Requirement already satisfied: numpy>=1.16.0 in c:\users\prakh\anaconda3\lib\site-packages (from yellowbrick) (1.23.5)
Requirement already satisfied: cycler>=0.10.0 in c:\users\prakh\anaconda3\lib\site-packages (from yellowbrick) (0.11.0)
Requirement already satisfied: scikit-learn>=1.0.0 in c:\users\prakh\anaconda3\lib\site-packages (from yellowbrick) (1.2.1)
Requirement already satisfied: scipy>=1.0.0 in c:\users\prakh\anaconda3\lib\site-packages (from yellowbrick) (1.10.0)
Requirement already satisfied: matplotlib!=3.0.0,>=2.0.2 in c:\users\prakh\anaconda3\lib\site-packages (from yellowbrick) (3.7.0)
Requirement already satisfied: kiwisolver>=1.0.1 in c:\users\prakh\anaconda3\lib\site-packages (from matplotlib!=3.0.0,>=2.0.2->yellowbrick) (1.4.4)
Requirement already satisfied: pyparsing>=2.3.1 in c:\users\prakh\anaconda3\lib\site-packages (from matplotlib!=3.0.0,>=2.0.2->yellowbrick) (3.0.9)
Requirement already satisfied: fonttools>=4.22.0 in c:\users\prakh\anaconda3\lib\site-packages (from matplotlib!=3.0.0,>=2.0.2->yellowbrick) (4.25.0)
Requirement already satisfied: contourpy>=1.0.1 in c:\users\prakh\anaconda3\lib\site-packages (from matplotlib!=3.0.0,>=2.0.2->yellowbrick) (1.0.5)
Requirement already satisfied: python-dateutil>=2.7 in c:\users\prakh\anaconda3\lib\site-packages (from matplotlib!=3.0.0,>=2.0.2->yellowbrick) (2.8.2)
Requirement already satisfied: pillow>=6.2.0 in c:\users\prakh\anaconda3\lib\site-packages (from matplotlib!=3.0.0,>=2.0.2->yellowbrick) (9.4.0)
Requirement already satisfied: packaging>=20.0 in c:\users\prakh\anaconda3\lib\site-packages (from matplotlib!=3.0.0,>=2.0.2->yellowbrick) (22.0)
Requirement already satisfied: threadpoolctl>=2.0.0 in c:\users\prakh\anaconda3\lib\site-packages (from scikit-learn>=1.0.0->yellowbrick) (2.2.0)
Requirement already satisfied: joblib>=1.1.1 in c:\users\prakh\anaconda3\lib\site-packages (from scikit-learn>=1.0.0->yellowbrick) (1.1.1)
Requirement already satisfied: six>=1.5 in c:\users\prakh\anaconda3\lib\site-packages (from python-dateutil>=2.7->matplotlib!=3.0.0,>=2.0.2->yellowbrick) (1.16.0)

from yellowbrick.target import FeatureCorrelation

feature_names = ['popularity', 'acousticness', 'danceability', 'energy', 'instrumentalness', 'liveness',
                 'loudness', 'speechiness', 'tempo', 'valence', 'duration_ms', 'explicit', 'key', 'mode', 'year']

X, Y = data[feature_names], data['popularity']

# Create a list of the feature names
features = np.array(feature_names)

# Instantiate the visualizer
visualizer = FeatureCorrelation(labels=features)

plt.rcParams['figure.figsize']=(10,5)
visualizer.fit(X, Y)     # Fit the data to the visualizer
visualizer.show()

<Axes: title={'center': 'Features correlation with dependent variable'}, xlabel='Pearson Correlation'>

Number of songs released over the decades

def year_to_decade(year):
    period_start = int(year/10) * 10
    year_decade = '{}s'.format(period_start)
    return year_decade

data['decade'] = data['year'].apply(year_to_decade)

sns.set(rc={'figure.figsize':(11 ,6)})
sns.countplot(data=data, x='decade')

<Axes: xlabel='decade', ylabel='count'>

Trend of various music features over decades

music_features = ['acousticness', 'danceability', 'energy', 'instrumentalness', 'liveness', 'valence']
fig = px.line(year_data, x='year', y=music_features,title='Trend of various music features over decades', 
              width=900, height=500)
fig.show()

Trend of loudness in the music over decades

fig = px.line(year_data, x='year', y='loudness',title='Trend of loudness in the music over decades')
fig.show()

Trend of various music features over top 10 genres

top10_genres = genre_data.nlargest(10, 'popularity')

fig = px.bar(top10_genres, x='genres', y=['valence', 'energy', 'danceability', 'acousticness'], barmode='stack',
            title='Trend of various music features over top 10 genres', width=900, height=650)
fig.show()

Conclusion :

a. Acousticness and Energy has a high correlation compared to other music features
b. The majority of the songs fall within the time range of 1950s to 2010s.
c. The level of energy in songs has progressively risen over time, while the instrumentalness has declined.
d. The level of acousticness in songs has significantly decreased over the years, particularly since the 1960s.
e. The trend of increasing loudness in songs is unmistakable and has reached its zenith in 2020.
f. Among the top 10 genres, energy and danceability are the most prominent characteristics.

top10_popular_artists = artist_data.nlargest(10, 'popularity')
print('Top 10 Artists that have the most popularity:')
top10_popular_artists[['popularity','artists']].sort_values('popularity',ascending=False)

Top 10 Artists that have the most popularity:

	popularity	artists
20966	93.0	Ritt Momney
14354	92.0	Lele Pons
15070	90.0	Los Legendarios
11764	89.0	Jerry Di
7463	88.0	Emilee
23687	88.0	Surf Mesa
28263	88.0	salem ilese
213	87.0	A7S
2343	86.0	Beltito
14378	86.0	Lenny Santos

top10_most_songs_artists = artist_data.nlargest(10, 'count')
print('Top 10 Artists that produced most songs:')
top10_most_songs_artists[['count','artists']].sort_values('count',ascending=False)

Top 10 Artists that produced most songs:

	count	artists
8367	3169	Francisco Canaro
28561	2422	Эрнест Хемингуэй
28560	2136	Эрих Мария Ремарк
8434	1459	Frank Sinatra
10714	1256	Ignacio Corsini
27109	1200	Vladimir Horowitz
1682	1146	Arturo Toscanini
2707	1103	Billie Holiday
12378	1061	Johnny Cash
7426	1023	Elvis Presley

Based on the findings of the exploratory data analysis (EDA), the following conclusions can be drawn:

1. The majority of the songs in the dataset were produced between the 1950s and 2010s.
2. There is a clear trend of increasing energy in songs over time.
3. The acousticness of songs has significantly decreased over the decades.
4. Loudness has consistently increased over the decades, with a noticeable peak in 2020.
5. Among the top 10 genres, energy and danceability are the most notable features.

Clustering Genres with K-Means

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.cluster import KMeans
import numpy as np

kmeans = KMeans(n_clusters=10)
#kmeans.set_params(n__jobs=-1)  # set number of jobs for parallel computing
cluster_pipeline = Pipeline([('scaler', StandardScaler()), ('kmeans', kmeans)])
X = genre_data.select_dtypes(np.number)
cluster_pipeline.fit(X)

Pipeline(steps=[('scaler', StandardScaler()),
                ('kmeans', KMeans(n_clusters=10))])

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

genre_data['cluster'] = cluster_pipeline.predict(X)
genre_data

	mode	genres	acousticness	danceability	duration_ms	energy	instrumentalness	liveness	loudness	speechiness	tempo	valence	popularity	key	cluster
0	1	21st century classical	0.979333	0.162883	1.602977e+05	0.071317	0.606834	0.361600	-31.514333	0.040567	75.336500	0.103783	27.833333	6	9
1	1	432hz	0.494780	0.299333	1.048887e+06	0.450678	0.477762	0.131000	-16.854000	0.076817	120.285667	0.221750	52.500000	5	4
2	1	8-bit	0.762000	0.712000	1.151770e+05	0.818000	0.876000	0.126000	-9.180000	0.047000	133.444000	0.975000	48.000000	7	3
3	1	[]	0.651417	0.529093	2.328809e+05	0.419146	0.205309	0.218696	-12.288965	0.107872	112.857352	0.513604	20.859882	7	1
4	1	a cappella	0.676557	0.538961	1.906285e+05	0.316434	0.003003	0.172254	-12.479387	0.082851	112.110362	0.448249	45.820071	7	1
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
2968	1	zolo	0.222625	0.547082	2.580991e+05	0.610240	0.143872	0.204206	-11.295878	0.061088	125.494919	0.596155	33.778943	9	3
2969	0	zouglou	0.161000	0.863000	2.063200e+05	0.909000	0.000000	0.108000	-5.985000	0.081300	119.038000	0.845000	58.000000	7	2
2970	1	zouk	0.263261	0.748889	3.060728e+05	0.622444	0.257227	0.089678	-10.289222	0.038778	101.965222	0.824111	46.666667	5	3
2971	0	zurich indie	0.993000	0.705667	1.984173e+05	0.172667	0.468633	0.179667	-11.453333	0.348667	91.278000	0.739000	0.000000	7	1
2972	1	zydeco	0.421038	0.629409	1.716717e+05	0.609369	0.019248	0.255877	-9.854825	0.050491	126.366087	0.808544	30.261905	7	3

2973 rows × 15 columns

# Visualizing the Clusters with t-SNE

from sklearn.manifold import TSNE

tsne_pipeline = Pipeline([('scaler', StandardScaler()), ('tsne', TSNE(n_components=2, verbose=1))])
genre_embedding = tsne_pipeline.fit_transform(X)
projection = pd.DataFrame(columns=['x', 'y'], data=genre_embedding)
projection['genres'] = genre_data['genres']
projection['cluster'] = genre_data['cluster']

fig = px.scatter(
    projection, x='x', y='y', color='cluster', hover_data=['x', 'y', 'genres'])
fig.show()

[t-SNE] Computing 91 nearest neighbors...
[t-SNE] Indexed 2973 samples in 0.013s...
[t-SNE] Computed neighbors for 2973 samples in 0.683s...
[t-SNE] Computed conditional probabilities for sample 1000 / 2973
[t-SNE] Computed conditional probabilities for sample 2000 / 2973
[t-SNE] Computed conditional probabilities for sample 2973 / 2973
[t-SNE] Mean sigma: 0.777516
[t-SNE] KL divergence after 250 iterations with early exaggeration: 76.106277
[t-SNE] KL divergence after 1000 iterations: 1.391782

Clustering Songs with K-Means

song_cluster_pipeline = Pipeline([('scaler', StandardScaler()), 
                                  ('kmeans', KMeans(n_clusters=20, 
                                   verbose=False))
                                 ], verbose=False)

X = data.select_dtypes(np.number)
number_cols = list(X.columns)
song_cluster_pipeline.fit(X)

Pipeline(steps=[('scaler', StandardScaler()),
                ('kmeans', KMeans(n_clusters=20, verbose=False))])

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

X

	valence	year	acousticness	danceability	duration_ms	energy	explicit	instrumentalness	key	liveness	loudness	mode	popularity	speechiness	tempo
0	0.0594	1921	0.98200	0.279	831667	0.211	0	0.878000	10	0.6650	-20.096	1	4	0.0366	80.954
1	0.9630	1921	0.73200	0.819	180533	0.341	0	0.000000	7	0.1600	-12.441	1	5	0.4150	60.936
2	0.0394	1921	0.96100	0.328	500062	0.166	0	0.913000	3	0.1010	-14.850	1	5	0.0339	110.339
3	0.1650	1921	0.96700	0.275	210000	0.309	0	0.000028	5	0.3810	-9.316	1	3	0.0354	100.109
4	0.2530	1921	0.95700	0.418	166693	0.193	0	0.000002	3	0.2290	-10.096	1	2	0.0380	101.665
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
170648	0.6080	2020	0.08460	0.786	301714	0.808	0	0.000289	7	0.0822	-3.702	1	72	0.0881	105.029
170649	0.7340	2020	0.20600	0.717	150654	0.753	0	0.000000	7	0.1010	-6.020	1	68	0.0605	137.936
170650	0.6370	2020	0.10100	0.634	211280	0.858	0	0.000009	4	0.2580	-2.226	0	76	0.0809	91.688
170651	0.1950	2020	0.00998	0.671	337147	0.623	1	0.000008	2	0.6430	-7.161	1	70	0.3080	75.055
170652	0.6420	2020	0.13200	0.856	189507	0.721	1	0.004710	7	0.1820	-4.928	1	74	0.1080	94.991

170653 rows × 15 columns

data

	valence	year	acousticness	artists	danceability	duration_ms	energy	explicit	id	instrumentalness	key	liveness	loudness	mode	name	popularity	release_date	speechiness	tempo	decade
0	0.0594	1921	0.98200	['Sergei Rachmaninoff', 'James Levine', 'Berli...	0.279	831667	0.211	0	4BJqT0PrAfrxzMOxytFOIz	0.878000	10	0.6650	-20.096	1	Piano Concerto No. 3 in D Minor, Op. 30: III. ...	4	1921	0.0366	80.954	1920s
1	0.9630	1921	0.73200	['Dennis Day']	0.819	180533	0.341	0	7xPhfUan2yNtyFG0cUWkt8	0.000000	7	0.1600	-12.441	1	Clancy Lowered the Boom	5	1921	0.4150	60.936	1920s
2	0.0394	1921	0.96100	['KHP Kridhamardawa Karaton Ngayogyakarta Hadi...	0.328	500062	0.166	0	1o6I8BglA6ylDMrIELygv1	0.913000	3	0.1010	-14.850	1	Gati Bali	5	1921	0.0339	110.339	1920s
3	0.1650	1921	0.96700	['Frank Parker']	0.275	210000	0.309	0	3ftBPsC5vPBKxYSee08FDH	0.000028	5	0.3810	-9.316	1	Danny Boy	3	1921	0.0354	100.109	1920s
4	0.2530	1921	0.95700	['Phil Regan']	0.418	166693	0.193	0	4d6HGyGT8e121BsdKmw9v6	0.000002	3	0.2290	-10.096	1	When Irish Eyes Are Smiling	2	1921	0.0380	101.665	1920s
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
170648	0.6080	2020	0.08460	['Anuel AA', 'Daddy Yankee', 'KAROL G', 'Ozuna...	0.786	301714	0.808	0	0KkIkfsLEJbrcIhYsCL7L5	0.000289	7	0.0822	-3.702	1	China	72	2020-05-29	0.0881	105.029	2020s
170649	0.7340	2020	0.20600	['Ashnikko']	0.717	150654	0.753	0	0OStKKAuXlxA0fMH54Qs6E	0.000000	7	0.1010	-6.020	1	Halloweenie III: Seven Days	68	2020-10-23	0.0605	137.936	2020s
170650	0.6370	2020	0.10100	['MAMAMOO']	0.634	211280	0.858	0	4BZXVFYCb76Q0Klojq4piV	0.000009	4	0.2580	-2.226	0	AYA	76	2020-11-03	0.0809	91.688	2020s
170651	0.1950	2020	0.00998	['Eminem']	0.671	337147	0.623	1	5SiZJoLXp3WOl3J4C8IK0d	0.000008	2	0.6430	-7.161	1	Darkness	70	2020-01-17	0.3080	75.055	2020s
170652	0.6420	2020	0.13200	['KEVVO', 'J Balvin']	0.856	189507	0.721	1	7HmnJHfs0BkFzX4x8j0hkl	0.004710	7	0.1820	-4.928	1	Billetes Azules (with J Balvin)	74	2020-10-16	0.1080	94.991	2020s

170653 rows × 20 columns

song_cluster_labels = song_cluster_pipeline.predict(X)
data['cluster_label'] = song_cluster_labels

# Visualizing the Clusters with PCA

from sklearn.decomposition import PCA

pca_pipeline = Pipeline([('scaler', StandardScaler()), ('PCA', PCA(n_components=2))])
song_embedding = pca_pipeline.fit_transform(X)
projection = pd.DataFrame(columns=['x', 'y'], data=song_embedding)
projection['title'] = data['name']
projection['cluster'] = data['cluster_label']

fig = px.scatter(
    projection, x='x', y='y', color='cluster', hover_data=['x', 'y', 'title'])
fig.show()

Recommender System

1. After analyzing and visualizing the data, it's evident that data points for similar genres and types of songs are clustered together.
2. This is expected since similar genres and songs share similar characteristics such as sound and time periods.
3. This observation can be utilized to build a recommendation system that recommends songs based on nearby data points to those that a user has already listened to.
4. To implement this, we can use Spotipy, a Python client for the Spotify Web API, to fetch data and query Spotify's catalog for songs.
5. To use Spotipy, we will need to install it using the "pip install spotipy" command and create an app on the Spotify Developer's page to obtain the developer's Client ID and secret key.

!pip install spotipy

Requirement already satisfied: spotipy in c:\users\prakh\anaconda3\lib\site-packages (2.23.0)
Requirement already satisfied: six>=1.15.0 in c:\users\prakh\anaconda3\lib\site-packages (from spotipy) (1.16.0)
Requirement already satisfied: redis>=3.5.3 in c:\users\prakh\anaconda3\lib\site-packages (from spotipy) (4.5.4)
Requirement already satisfied: urllib3>=1.26.0 in c:\users\prakh\anaconda3\lib\site-packages (from spotipy) (1.26.14)
Requirement already satisfied: requests>=2.25.0 in c:\users\prakh\anaconda3\lib\site-packages (from spotipy) (2.28.1)
Requirement already satisfied: async-timeout>=4.0.2 in c:\users\prakh\anaconda3\lib\site-packages (from redis>=3.5.3->spotipy) (4.0.2)
Requirement already satisfied: charset-normalizer<3,>=2 in c:\users\prakh\anaconda3\lib\site-packages (from requests>=2.25.0->spotipy) (2.0.4)
Requirement already satisfied: certifi>=2017.4.17 in c:\users\prakh\anaconda3\lib\site-packages (from requests>=2.25.0->spotipy) (2022.12.7)
Requirement already satisfied: idna<4,>=2.5 in c:\users\prakh\anaconda3\lib\site-packages (from requests>=2.25.0->spotipy) (3.4)

import spotipy
from spotipy.oauth2 import SpotifyClientCredentials
from collections import defaultdict

sp = spotipy.Spotify(auth_manager=SpotifyClientCredentials(client_id='e46c345f7f9a42f3bdf1652714ae64f4',
                                                           client_secret='d207bd6db1304f3fb8051da833a6f25e'))

def find_song(name, year):
    song_data = defaultdict()
    results = sp.search(q= 'track: {} year: {}'.format(name,year), limit=1)
    if results['tracks']['items'] == []:
        return None

    results = results['tracks']['items'][0]
    track_id = results['id']
    audio_features = sp.audio_features(track_id)[0]

    song_data['name'] = [name]
    song_data['year'] = [year]
    song_data['explicit'] = [int(results['explicit'])]
    song_data['duration_ms'] = [results['duration_ms']]
    song_data['popularity'] = [results['popularity']]

    for key, value in audio_features.items():
        song_data[key] = value

    return pd.DataFrame(song_data)

from collections import defaultdict
from sklearn.metrics import euclidean_distances
from scipy.spatial.distance import cdist
import difflib

number_cols = ['valence', 'year', 'acousticness', 'danceability', 
               'duration_ms', 'energy', 'explicit','instrumentalness', 
               'key', 'liveness', 'loudness', 'mode', 'popularity', 
               'speechiness', 'tempo']


def get_song_data(song, spotify_data):
    
    try:
        song_data = spotify_data[(spotify_data['name'] == song['name']) & (spotify_data['year'] == song['year'])].iloc[0]
        return song_data
    
    except IndexError:
        return find_song(song['name'], song['year'])
        

def get_mean_vector(song_list, spotify_data):
    
    song_vectors = []
    
    for song in song_list:
        song_data = get_song_data(song, spotify_data)
        if song_data is None:
            print('Warning: {} does not exist in Spotify or in database'.format(song['name']))
            continue
        song_vector = song_data[number_cols].values
        song_vectors.append(song_vector)  
    
    song_matrix = np.array(list(song_vectors))
    return np.mean(song_matrix, axis=0)


def flatten_dict_list(dict_list):
    
    flattened_dict = defaultdict()
    for key in dict_list[0].keys():
        flattened_dict[key] = []
    
    for dictionary in dict_list:
        for key, value in dictionary.items():
            flattened_dict[key].append(value)
            
    return flattened_dict


def recommend_songs( song_list, spotify_data, n_songs=10):
    
    metadata_cols = ['name', 'year', 'artists']
    song_dict = flatten_dict_list(song_list)
    
    song_center = get_mean_vector(song_list, spotify_data)
    scaler = song_cluster_pipeline.steps[0][1]
    scaled_data = scaler.transform(spotify_data[number_cols])
    scaled_song_center = scaler.transform(song_center.reshape(1, -1))
    distances = cdist(scaled_song_center, scaled_data, 'cosine')
    index = list(np.argsort(distances)[:, :n_songs][0])
    
    rec_songs = spotify_data.iloc[index]
    rec_songs = rec_songs[~rec_songs['name'].isin(song_dict['name'])]
    return rec_songs[metadata_cols].to_dict(orient='records')

Here, it gives a recommendation list of songs according to the input given below :

recommend_songs(
    [
        {'name': 'Love Story', 'year':2009, 'artists':'Taylor Swift'},
        {'name': 'Perfect', 'year': 2017, 'artists':'Ed Sheeran'},
        {'name': 'Truly Madly Deeply', 'year': 1997, 'artists':'Daniel Jones'},
    ], data)

[{'name': 'Before You Go', 'year': 2019, 'artists': "['Lewis Capaldi']"},
 {'name': 'Before You Go', 'year': 2019, 'artists': "['Lewis Capaldi']"},
 {'name': 'Used to Be', 'year': 2018, 'artists': "['AJ Mitchell']"},
 {'name': 'mirrorball', 'year': 2020, 'artists': "['Taylor Swift']"},
 {'name': 'Oh Ana', 'year': 2007, 'artists': "['Mother Mother']"},
 {'name': 'The Village', 'year': 2017, 'artists': "['Wrabel']"},
 {'name': 'Sweet Night', 'year': 2020, 'artists': "['V']"},
 {'name': 'The Only Boy Awake', 'year': 2016, 'artists': "['Meadows']"},
 {'name': 'Like A Cowboy', 'year': 2020, 'artists': "['Parker McCollum']"},
 {'name': 'Someone You Loved', 'year': 2019, 'artists': "['Lewis Capaldi']"}]